How to use this checklist
This expands the six-step checklist in our AI-shopper-ready guide. Each item follows the same pattern: what it is, why an agent cares, how to check it, and whether it's your job or Rendered Fits'. Work through Part 1 first — general catalogue hygiene any store can improve. Part 2 is the fit-specific layer almost no fashion store has solved on its own, and the part one Rendered Fits install closes in a single step.
Part 1 — Core product data (your job)
These two checks apply to any e-commerce store, fashion or otherwise. They are not Rendered Fits' responsibility — they are your theme, your product data, and your ongoing catalogue hygiene.
1. Structured core product data
What it is: price, availability, images and product attributes exposed as Schema.org Product/Offer JSON-LD, not only as page copy.
Why it matters: an agent parsing your PDP needs structured fields to reason with. It can infer meaning from prose, but it cannot reliably match "beautiful floaty dress" against a shopper's stated requirements the way it can match a material or offers.price field.
How to verify: run the product page through Google's Rich Results Test and confirm a Product block with a populated offers field, not just warnings.
Covered by: you and your theme. Rendered Fits does not touch this.
2. A machine-readable size guide
What it is: your size chart published as an on-page HTML table, measurements in centimetres per size — not an image, and not a linked PDF.
Why it matters: a crawler or agent reads text, not pixels. A size guide baked into a graphic is invisible to it no matter how clearly a human can read it.
How to verify: view page source (or use your browser's "select all" on the size guide) and confirm the numbers are selectable text, not part of an <img>.
Covered by: you and your PDP content. This is the static baseline Part 2 builds on top of.
Part 2 — The fit layer (Rendered Fits, on install)
This is the part almost no fashion store has solved, because fit is not a field on most product pages — it is a paragraph in a size-chart tab, if it exists at all. Installing Rendered Fits publishes all six of the following automatically, on your own domain, with no extra configuration.
3. Machine-readable fit and sizing per variant
What it is: fit type, size guidance and a confidence score, available as structured data for each product and each variant.
Why it matters: "runs small" buried in a customer review is not something an agent can reliably parse and act on. The same fact as a structured field is.
How to verify: request GET /apps/rendered-fits/fit/{productId} on your own store domain and confirm it returns fit type, size guidance and a confidence score.
Covered by: Rendered Fits, automatically on install.
4. Agent-callable endpoints on your own domain
What it is: URLs on your own hostname that answer fit and capability queries directly, rather than making an agent guess from page text.
Why it matters: an agent can call your store directly for a structured answer instead of scraping and inferring — the difference between an API and a guess.
How to verify: request /apps/rendered-fits/fit/{productId}, /apps/rendered-fits/fit-jsonld/{productId} and /apps/rendered-fits/agent-manifest on your own storefront domain.
Covered by: Rendered Fits, automatically on install.
5. A Storefront-readable fit metafield
What it is: fit profiles published to the renderedfits.fit_profile Storefront metafield.
Why it matters: apps and agents already integrated at the Shopify Storefront API layer can read fit data the same way they read any other product field — no custom endpoint required.
How to verify: in Shopify admin, go to Settings > Custom data > Products and look for the metafield, or query the Storefront API for it directly.
Covered by: Rendered Fits, automatically on install.
6. A hosted MCP interface
What it is: a Model Context Protocol server so MCP-capable assistants and shopping copilots can query fit-profile, size-recommendation and fit-summary as tools, against a public OpenAPI 3.1 specification.
Why it matters: MCP is becoming the standard way assistants call external tools. Without it, an MCP-capable agent has no route to your fit data at all.
How to verify: confirm the public OpenAPI spec is reachable, then test an authenticated call to POST https://api.renderedfits.com/api/v1/mcp with a per-shop key.
Covered by: Rendered Fits, automatically on install.
7. A fit signal grounded in real outcomes
What it is: fit and size guidance drawn from real try-on sessions and post-purchase kept/returned outcomes, not a static size chart.
Why it matters: data grounded in what shoppers actually did carries more weight than a size chart nobody has checked against reality.
How to verify: no merchant-facing toggle here — it's the data model underneath everything above, not a separate setting.
Covered by: Rendered Fits' data model, not merchant-configurable.
8. A visual answer for the human shopper
What it is: a photorealistic try-on widget on the product page, rendering the garment on the shopper's own photo.
Why it matters: even a well-answered agent query cannot show a specific shopper what a garment will look like on them. That question still needs a visual answer, for the human making the final call.
How to verify: open a live product page and confirm the try-on block appears and produces a render.
Covered by: Rendered Fits' capability — but placement is the one manual step, done by you through the Shopify theme editor.
The checklist at a glance
| Item | Who covers it | Verify with |
|---|---|---|
| 1. Structured Product/Offer schema | You | Rich Results Test |
| 2. Machine-readable size guide | You | View page source |
| 3. Fit and sizing per variant | Rendered Fits | /apps/rendered-fits/fit/{id} |
| 4. Agent-callable endpoints | Rendered Fits | fit / fit-jsonld / agent-manifest |
| 5. Storefront fit metafield | Rendered Fits | Shopify admin custom data |
| 6. Hosted MCP interface | Rendered Fits | openapi.json / POST /api/v1/mcp |
| 7. Outcome-grounded fit signal | Rendered Fits | Not merchant-configurable |
| 8. Visual try-on for the human | Rendered Fits + you (placement) | View a live PDP |
Frequently asked questions
How do I know if my store is AI-shopper-ready?
Work through the eight checks above. Items 1–2 are general good practice you or your theme handle. Items 3–8 are the fit-specific layer almost no store has solved. Install Rendered Fits and 3–8 go live automatically; you remain responsible for 1–2 and for placing the try-on widget.
Does Rendered Fits handle the whole checklist?
No. It handles the fit layer — items 3–8 — automatically, with no extra configuration. Your core Product/Offer schema and size-guide formatting remain your responsibility; Rendered Fits does not touch general product data.
What do I still have to do myself?
Three things: keep core product data as proper Schema.org Product/Offer markup, keep your size guide as on-page HTML text rather than an image or PDF, and place the Rendered Fits try-on widget on your product pages yourself, through the Shopify theme editor.
How long does this take?
Installing Rendered Fits, covering items 3–8, takes under an hour from existing product photography with no further configuration needed. Tidying core Product schema and size-guide formatting depends on your existing catalogue, so there's no single timeframe for that part.
Do I need to configure anything after installing Rendered Fits?
No extra configuration is required for the agent-facing fit layer — the fit endpoints, the Storefront metafield and the MCP server come online with the app. The one thing you place yourself is the shopper-facing try-on widget, added through the Shopify theme editor.